ipykernel-mcp
An MCP server that manages an IPython kernel, allowing LLMs to execute Python code in a project's virtual environment.
README
ipykernel-mcp
An MCP server that manages an IPython kernel, allowing LLMs to execute Python code in a project's virtual environment.
Built with FastMCP and jupyter-client.
Tools
| Tool | Description |
|---|---|
kernel_start(project_dir) |
Start a kernel using the .venv from the given project directory |
kernel_execute(code, timeout) |
Execute code and return tagged output blocks ([stdout], [stderr], [result], [error], images). On timeout, returns partial output + [pending] with a msg_id |
kernel_get_output(msg_id, timeout) |
Retrieve remaining output for a timed-out execution. Auto-cleans up once complete |
kernel_interrupt() |
Send SIGINT to cancel a long-running execution without losing kernel state |
kernel_restart() |
Restart the kernel, clearing all variables and state |
kernel_stop() |
Stop the kernel and clean up resources |
kernel_status() |
Return kernel status: running, alive, project_dir, connection_file, pending_executions, ports |
Installation
uv sync
The project directory passed to kernel_start must contain a .venv with ipykernel installed.
Usage
Run the MCP server:
ipykernel-mcp
Or add it to your MCP client configuration:
{
"mcpServers": {
"ipykernel-mcp": {
"command": "uvx",
"args": ["--from", "git+https://github.com/0x0L/ipykernel-mcp", "ipykernel-mcp"]
}
}
}
Monitoring
jupyter_watch can monitor kernel output (stdout, stderr, display data) in real-time in a browser:
npx github:0x0L/jupyter_watch <connection_file>
The connection file path is printed by kernel_start when the kernel starts.
Development
uv sync --dev
uv run pytest tests/ -v
Pre-commit hooks are configured to run formatting, linting, and type checking:
uv run pre-commit install
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.